Urban Traffic Prediction from Spatio-Temporal Data Using Deep Meta Learning
Explore this paper's citation graph
Summary
This work proposed a deep-meta-learning based model, entitled ST-MetaNet, to collectively predict traffic in all location at once, consisting of a recurrent neural network to encode the traffic, a meta graph attention network to capture diverse spatial correlations, and a meta recurrent Neural network to consider diverse temporal correlations.
- Type
- article
- Published
- 2019-07-25
- Cited by
- 645
- References
- 31
- OpenAlex
- https://openalex.org/W2950817888
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:174773261
Keywords
Timestamp, Computer science, ENCODE, Data mining, Encoder
References
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- Prediction of human emergency behavior and their mobility following large-scale disaster
- Traffic Flow Prediction for Road Transportation Networks With Limited Traffic Data
- Adaptive dissimilarity index for measuring time series proximity
- T-drive: driving directions based on taxi trajectories
- Road Traffic Congestion Monitoring in Social Media with Hinge-Loss Markov Random Fields
- Multi-Task Learning for Spatio-Temporal Event Forecasting
- CityMomentum: an online approach for crowd behavior prediction at a citywide level
- Big data and its technical challenges
- Urban computing with taxicabs
- Urban Computing: Concepts, Methodologies, and Applications
- Urban Water Quality Prediction Based on Multi-Task Multi-View Learning
- GSpartan: a Geospatio-Temporal Multi-task Learning Framework for Multi-location Prediction
- Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction
- Dynamic filter networks for predicting unobserved views
- Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting
- Graph Attention Networks
- PredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs
- Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction
- Meta Multi-Task Learning for Sequence Modeling
Cited by
- Incorporating Dynamicity of Transportation Network With Multi-Weight Traffic Graph Convolutional Network for Traffic Forecasting
- VLUC: An Empirical Benchmark for Video-Like Urban Computing on Citywide Crowd and Traffic Prediction
- Building Effective Large-Scale Traffic State Prediction System: Traffic4cast Challenge Solution
- Matrix Factorization for Spatio-Temporal Neural Networks with Applications to Urban Flow Prediction
- Potential Passenger Flow Prediction: A Novel Study for Urban Transportation Development
- Urban flow prediction from spatiotemporal data using machine learning: A survey
- Spatial-Temporal Transformer Networks for Traffic Flow Forecasting
- DDP-GCN: Multi-graph convolutional network for spatiotemporal traffic forecasting
- Reinforced Spatiotemporal Attentive Graph Neural Networks for Traffic Forecasting
- Global Spatial-Temporal Graph Convolutional Network for Urban Traffic Speed Prediction
- BuildSenSys: Reusing Building Sensing Data for Traffic Prediction With Cross-Domain Learning
- Dynamic Public Resource Allocation Based on Human Mobility Prediction
- Dynamic Flow Distribution Prediction for Urban Dockless E-Scooter Sharing Reconfiguration
- Hierarchically Structured Transformer Networks for Fine-Grained Spatial Event Forecasting
- A Comprehensive Survey on Traffic Prediction
- Spatiotemporal Data Fusion in Graph Convolutional Networks for Traffic Prediction
- Learning Geo-Contextual Embeddings for Commuting Flow Prediction
- Spatio-Temporal Meta Learning for Urban Traffic Prediction
- DJEnsemble: On the Selection of a Disjoint Ensemble of Deep Learning Black-Box Spatio-temporal Models
- Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks
Related papers
- An algorithm for timestamp removal for panorama video surveillance
- The ENCODE Project Decoded
- A Lifelog System Specialized to Record Timestamp of Daily Works
- The Study of OCDMA Encode/Decode Using Multilayer Films
- Efficient Timestamps for Capturing Causality
- Timestamp representations for virtual sequences
- Using The ENCODE Resource For Functional Annotation Of Genetic Variants
- A Comparative Study of Forecasting Problems on Electrical Load Timeseries Data using Deep Learning Techniques